© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78884
    Prev
    Next
    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     میلی
    -0.09
     monat
    -0.08
     altra
    -0.08
     Als
    -0.08
     month
    -0.07
     rapidly
    -0.07
     Wenn
    -0.07
     strpos
    -0.07
     somm
    -0.07
     somme
    -0.07
    POSITIVE LOGITS
    _Item
    0.10
    	Item
    0.09
    	item
    0.09
    Cargo
    0.09
     cargo
    0.09
    _ITEMS
    0.09
    <Item
    0.09
    Lean
    0.09
    (items
    0.09
     izinto
    0.08
    Activations Density 0.013%

    No Known Activations